def _process_action_step()

in src/smolagents/gradio_ui.py [0:0]

• 54 lines of code
• 16 McCabe index (conditional complexity)

def _process_action_step(step_log: ActionStep, skip_model_outputs: bool = False) -> Generator:
    """
    Process an [`ActionStep`] and yield appropriate Gradio ChatMessage objects.

    Args:
        step_log ([`ActionStep`]): ActionStep to process.
        skip_model_outputs (`bool`): Whether to skip model outputs.

    Yields:
        `gradio.ChatMessage`: Gradio ChatMessages representing the action step.
    """
    import gradio as gr

    # Output the step number
    step_number = f"Step {step_log.step_number}"
    if not skip_model_outputs:
        yield gr.ChatMessage(role=MessageRole.ASSISTANT, content=f"**{step_number}**", metadata={"status": "done"})

    # First yield the thought/reasoning from the LLM
    if not skip_model_outputs and getattr(step_log, "model_output", ""):
        model_output = _clean_model_output(step_log.model_output)
        yield gr.ChatMessage(role=MessageRole.ASSISTANT, content=model_output, metadata={"status": "done"})

    # For tool calls, create a parent message
    if getattr(step_log, "tool_calls", []):
        first_tool_call = step_log.tool_calls[0]
        used_code = first_tool_call.name == "python_interpreter"

        # Process arguments based on type
        args = first_tool_call.arguments
        if isinstance(args, dict):
            content = str(args.get("answer", str(args)))
        else:
            content = str(args).strip()

        # Format code content if needed
        if used_code:
            content = _format_code_content(content)

        # Create the tool call message
        parent_message_tool = gr.ChatMessage(
            role=MessageRole.ASSISTANT,
            content=content,
            metadata={
                "title": f"🛠️ Used tool {first_tool_call.name}",
                "status": "done",
            },
        )
        yield parent_message_tool

    # Display execution logs if they exist
    if getattr(step_log, "observations", "") and step_log.observations.strip():
        log_content = step_log.observations.strip()
        if log_content:
            log_content = re.sub(r"^Execution logs:\s*", "", log_content)
            yield gr.ChatMessage(
                role=MessageRole.ASSISTANT,
                content=f"```bash\n{log_content}\n",
                metadata={"title": "📝 Execution Logs", "status": "done"},
            )

    # Display any images in observations
    if getattr(step_log, "observations_images", []):
        for image in step_log.observations_images:
            path_image = AgentImage(image).to_string()
            yield gr.ChatMessage(
                role=MessageRole.ASSISTANT,
                content={"path": path_image, "mime_type": f"image/{path_image.split('.')[-1]}"},
                metadata={"title": "🖼️ Output Image", "status": "done"},
            )

    # Handle errors
    if getattr(step_log, "error", None):
        yield gr.ChatMessage(
            role=MessageRole.ASSISTANT, content=str(step_log.error), metadata={"title": "💥 Error", "status": "done"}
        )

    # Add step footnote and separator
    yield gr.ChatMessage(
        role=MessageRole.ASSISTANT,
        content=get_step_footnote_content(step_log, step_number),
        metadata={"status": "done"},
    )
    yield gr.ChatMessage(role=MessageRole.ASSISTANT, content="-----", metadata={"status": "done"})